Systematic refinement of surrogate modelling procedure for useful application to building energy problems
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
Systematic procedures for applying surrogate model development to building energy problems have limited adoption and struggle to incorporate advancements in broader machine learning research. This work demonstrates an iterative approach that encompasses: Establishing clear, consistent baseline performance thresholds.Assembling a comprehensive set of domain-relevant evaluation metrics, including rigorous bounds on error and emphasis on regions of interest within the broader problem space.Characterizing and adapting the problem space using sub-sampling and pre-processing techniques.Accounting for variability, randomness and complexity in the building energy problem definition, data sampling and surrogate model training.Refining the metamodel decision space defining the neural network architecture and training algorithms, and explored by hyperparameter optimization methods. In addition to demonstrating improved performance predicting aggregate annual heating and cooling demands for an illustrative office case, accuracy, bias and bounds on error were all brought within domain-relevant thresholds for net zero regions of interest.Highlights Iterative refinement of surrogate modelling procedure for building energy problemsConsideration of complexity and variability in energy data, problem and surrogateAddition of key dimensions to performance evaluation useful for domain applicationGreatly improved predictive value for net zero building energy regions of interestSystematic shift in hyperparameter tuning towards deep learning configurations
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it